Training in progress, step 28500, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f58101992470ce99c1c24e2ed6ac1048281fa6539f6045c9dff060f69941d5
+oid sha256:c9d7a9a80fc16ae19f3ee016e1f87ebbe28f8e5c54d2dee20067ac1375b3a699
 size 4978139416

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6704070a643620f09ad45b4926d920d7c7503d06723489d09b8e5566b2037939
+oid sha256:6412766255f9548b27afe82cfd466bfa83c0ceff5e923f6bd16707cb31228ca1
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4548ca236f4173864dbd0ca1a1498544aaf94a4e29a4240dab5c4e4067bc8c43
+oid sha256:bb1d84e520f4f8a65b7489c9592eba3324b25ef0380fb698f857e6540f071004
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01741ba2843fcc38342b1b30b163edc00ac6120a04533362fb33d9ecac4ce1fe
+oid sha256:54b7c6a6814674e66826f920adadd693d50e8c9564cda211cba81879f559c0af
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4f04843d80970cd259c83429daf5f235586900bc4e8d66f6edb21ed7d2feb79
+oid sha256:7cf7c52a861212ad700d353d281972076097e14210eec92b789d70cbdc6a0277
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.913281414439066,
+  "epoch": 11.997474215954536,
   "eval_steps": 100,
-  "global_step": 28300,
+  "global_step": 28500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4535,6 +4535,38 @@
       "eval_samples_per_second": 25.816,
       "eval_steps_per_second": 3.228,
       "step": 28300
+    },
+    {
+      "epoch": 11.96,
+      "grad_norm": 13.059289932250977,
+      "learning_rate": 3.0293992932862192e-05,
+      "loss": 1.1318,
+      "step": 28400
+    },
+    {
+      "epoch": 11.96,
+      "eval_cer": 0.4224341050408666,
+      "eval_loss": 2.1082444190979004,
+      "eval_runtime": 393.3473,
+      "eval_samples_per_second": 24.096,
+      "eval_steps_per_second": 3.013,
+      "step": 28400
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 5.903038501739502,
+      "learning_rate": 3.0223321554770317e-05,
+      "loss": 1.1131,
+      "step": 28500
+    },
+    {
+      "epoch": 12.0,
+      "eval_cer": 0.41807125259082556,
+      "eval_loss": 1.7783021926879883,
+      "eval_runtime": 365.8673,
+      "eval_samples_per_second": 25.906,
+      "eval_steps_per_second": 3.239,
+      "step": 28500
     }
   ],
   "logging_steps": 100,
@@ -4542,7 +4574,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.101048540517328e+20,
+  "total_flos": 3.122274035580518e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null